© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10617
    Prev
    Next
    INDEX
    Explanations

    infectious diseases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ter
    -0.19
    çŁ¾
    -0.18
    arity
    -0.18
    hec
    -0.17
    åIJĦåįķä½į
    -0.17
    ort
    -0.17
    retrieve
    -0.16
    çĶ¨éĢĶ
    -0.16
    å®ĥåı¯ä»¥
    -0.16
    ayan
    -0.16
    POSITIVE LOGITS
    ../../../
    0.22
    ä¸ĸ人
    0.20
    æĢ§çĸ¾çĹħ
    0.18
    ible
    0.18
    ounter
    0.17
    ãģįãģŁ
    0.17
    çĦ¶æĺ¯
    0.17
    IBLE
    0.17
    ibia
    0.17
    å¢ħ
    0.16
    Activations Density 0.022%

    No Known Activations